File size: 3,744 Bytes
b98cec2 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 |
import torch
import torch.nn as nn
import torch.nn.functional as F
class SEBasicBlock(nn.Module):
expansion = 1
def __init__(self, inplanes, planes, stride=1, downsample=None, reduction=8):
super(SEBasicBlock, self).__init__()
self.conv1 = nn.Conv2d(inplanes, planes, kernel_size=3, stride=stride, padding=1, bias=False)
self.bn1 = nn.BatchNorm2d(planes)
self.conv2 = nn.Conv2d(planes, planes, kernel_size=3, padding=1, bias=False)
self.bn2 = nn.BatchNorm2d(planes)
self.relu = nn.ReLU(inplace=True)
self.se = SELayer(planes, reduction)
self.downsample = downsample
self.stride = stride
def forward(self, x):
residual = x
out = self.conv1(x)
out = self.relu(out)
out = self.bn1(out)
out = self.conv2(out)
out = self.bn2(out)
out = self.se(out)
if self.downsample is not None:
residual = self.downsample(x)
out += residual
out = self.relu(out)
return out
class SELayer(nn.Module):
def __init__(self, channel, reduction=8):
super(SELayer, self).__init__()
self.avg_pool = nn.AdaptiveAvgPool2d(1)
self.fc = nn.Sequential(
nn.Linear(channel, channel // reduction),
nn.ReLU(inplace=True),
nn.Linear(channel // reduction, channel),
nn.Sigmoid()
)
def forward(self, x):
b, c, _, _ = x.size()
y = self.avg_pool(x).view(b, c)
y = self.fc(y).view(b, c, 1, 1)
return x * y
class audioEncoder(nn.Module):
def __init__(self, layers, num_filters, **kwargs):
super(audioEncoder, self).__init__()
block = SEBasicBlock
self.inplanes = num_filters[0]
self.conv1 = nn.Conv2d(1, num_filters[0] , kernel_size=7, stride=(2, 1), padding=3,
bias=False)
self.bn1 = nn.BatchNorm2d(num_filters[0])
self.relu = nn.ReLU(inplace=True)
self.layer1 = self._make_layer(block, num_filters[0], layers[0])
self.layer2 = self._make_layer(block, num_filters[1], layers[1], stride=(2, 2))
self.layer3 = self._make_layer(block, num_filters[2], layers[2], stride=(2, 2))
self.layer4 = self._make_layer(block, num_filters[3], layers[3], stride=(1, 1))
out_dim = num_filters[3] * block.expansion
for m in self.modules():
if isinstance(m, nn.Conv2d):
nn.init.kaiming_normal_(m.weight, mode='fan_out', nonlinearity='relu')
elif isinstance(m, nn.BatchNorm2d):
nn.init.constant_(m.weight, 1)
nn.init.constant_(m.bias, 0)
def _make_layer(self, block, planes, blocks, stride=1):
downsample = None
if stride != 1 or self.inplanes != planes * block.expansion:
downsample = nn.Sequential(
nn.Conv2d(self.inplanes, planes * block.expansion,
kernel_size=1, stride=stride, bias=False),
nn.BatchNorm2d(planes * block.expansion),
)
layers = []
layers.append(block(self.inplanes, planes, stride, downsample))
self.inplanes = planes * block.expansion
for i in range(1, blocks):
layers.append(block(self.inplanes, planes))
return nn.Sequential(*layers)
def forward(self, x):
x = self.conv1(x)
x = self.bn1(x)
x = self.relu(x)
x = self.layer1(x)
x = self.layer2(x)
x = self.layer3(x)
x = self.layer4(x)
x = torch.mean(x, dim=2, keepdim=True)
x = x.view((x.size()[0], x.size()[1], -1))
x = x.transpose(1, 2)
return x |